> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getoneprofile.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Pick the audience of your own wizard run

> Picks one of the audiences the signed-in person's wizard run in their active workspace offers (the run `GET /own-runs/` lists), as the wizard page's pick does: finds 100 people of it, researches the top 10 and writes their first messages. Needs no session token: the sign-in finds the run, so an AI app connected to the workspace can pick it. 404 when the person has no run still to finish; 409 when the pick is refused where it stands (no such audience, too few people, people already found).



## OpenAPI

````yaml /openapi.json put /onboarding-wizard/own-runs/current/segment/
openapi: 3.1.0
info:
  contact:
    email: support@getoneprofile.ai
    name: Oneprofile Support
  description: >-
    REST API reference for Oneprofile, the GTM data layer for your CRM. Manage
    tables, enrichments, and integrations. Authenticate with an API key to get
    started.
  termsOfService: https://www.getoneprofile.ai/terms
  title: API Reference | Oneprofile
  version: '0.0'
servers:
  - url: https://api.getoneprofile.ai
security: []
tags:
  - description: >-
      The docked AI Assistant: its general chat about the workspace and the
      product, streamed as Server-Sent Events, and the one list of a person's
      threads across every assistant, with pin, rename, delete and the
      search-to-table link, and the read of a web page a person links.
    name: assistant
  - description: >-
      The messages a person keeps to send the assistant again: the ones the
      workspace saved and the ones that ship with the product, with save,
      rename, edit and delete.
    name: assistant-prompt
  - description: >-
      Granted workspace actions: what the AI Assistant proposed or applied in a
      conversation, the approve and dismiss decisions on each card, the
      workspace's spend threshold and default grants, and the eight verbs.
    name: workspace-actions
  - description: >-
      The Getting started checklist: a workspace's progress through the six
      steps from its first people search to its first launched sequence.
    name: onboarding
  - description: Senders, connected mailboxes, tags, and the Google connect flow.
    name: senders
  - description: The workspace do-not-contact list, enforced before every send.
    name: suppression
  - description: >-
      The workspace's recontact rule: how long before anyone hears from us
      again.
    name: contact_cooldown
  - description: 'Sequence authoring: the graph, the table-backed audience, previews.'
    name: sequences
  - description: >-
      The outbound agent behind a sequence: the voice it writes in, its
      per-message prompts, what it wrote and what people told it.
    name: outbound-agents
  - description: >-
      The LinkedIn channel: connecting an account to a sender, its safety limits
      and history, and the protocol the browser extension speaks.
    name: linkedin
  - description: >-
      The approval queue: everything waiting on a person across every sender and
      channel, and the workspace's manual or automatic modes per channel.
    name: outreach
  - description: 'The unified outreach inbox: threads, replies, labels, events.'
    name: inbox
  - description: 'The AI reply layer: workspace settings, drafts, and approval.'
    name: inbox-ai
  - description: Notification rules, per-user preferences, and the Slack connection.
    name: notifications
  - description: Endpoints for seeing all available integration types.
    name: integration-types
  - description: Endpoints for listing, checking and deleting integrations.
    name: integrations
  - description: >-
      Create, preview and update an integration of any type: the body's
      integration_type picks the config and credentials it takes.
    name: integration-specific
  - description: Endpoints for the generic OAuth install/claim app-listings engine.
    name: app-listings
  - description: Endpoints for creating and managing API keys.
    name: apikey
  - description: >-
      AI apps connected to the workspace: Claude, ChatGPT, Claude Code or any
      other MCP client a person signed in to Oneprofile's MCP server with.
    name: ai_apps
  - description: Endpoints for managing billing and subscription information.
    name: billing
  - description: >-
      Accounts: every company the workspace's tables name, with the people at
      it, its key facts, its tables, its org chart and what went to its people;
      the tables that feed it (Sources) and the merges a person made.
    name: accounts
  - description: Endpoints for creating and managing tables.
    name: tables
  - description: Endpoints for table columns, formula previews, and on-demand column runs.
    name: table-columns
  - description: Endpoints for table rows and manual cell edits.
    name: table-rows
  - description: Endpoints for observing and cancelling table recompute runs.
    name: table-runs
  - description: >-
      Endpoints for org-shared per-column display preferences: hidden, pinned,
      width, and color tint.
    name: table-ui-prefs
  - description: >-
      Endpoints for the org-shared names given to the column tint palette: what
      this organization calls each color. Org-level, not per-table.
    name: table-column-color-labels
  - description: >-
      Endpoints for the enrichment action catalog, model list, presets, draft
      generation, and saved agents.
    name: table-enrichments
  - description: >-
      Endpoints for an agent's Preview: example rows run one at a time, and a
      Looks good on each. Needs work lives under agent-learnings.
    name: agent-training
  - description: >-
      An agent's learnings, the one-line rules it follows on every output, and
      the thumbs down that teaches them: give one with what was wrong, list the
      ones on a subject, Undo one, and price the redo it would run.
    name: agent-learnings
  - description: >-
      The durable audit trail of a table's enrichment actions: configured,
      edited, run, cancelled, and settled cost.
    name: table-enrichment-audit-logs
  - description: Endpoints for saving and applying column templates.
    name: table-templates
  - description: Server-sent change feed for a table's grid.
    name: table-events
  - description: 'Endpoints for org-shared saved table views: sort, filters, hidden columns.'
    name: table-views
  - description: >-
      Endpoints for PER-USER table preferences: favorites and recently opened.
      Unlike the rest of the table surface these are personal, so two members of
      one organization legitimately see different answers.
    name: table-user-prefs
  - description: >-
      Endpoints for building a table from an uploaded CSV: upload and preview
      the inferred columns, commit the reviewed mapping, then poll the row load.
    name: table-imports
  - description: Endpoint for downloading a table's rows as CSV.
    name: table-export
  - description: >-
      Endpoints for the integration a table imports from: attach and preview it,
      promote imported fields into columns, and run the import on demand.
    name: table-sources
  - description: >-
      Endpoints for the webhook URL an app or a tool of your own sends records
      to: what can send them, make the URL, show it again, replace it, revoke
      it, save the app's secrets, resume a paused feed, and read and retry the
      deliveries that did not fit.
    name: table-webhooks
  - description: >-
      Endpoints for a table's recurring import cadence: set it, pause it, and
      read the next fire times.
    name: table-schedules
  - description: >-
      Endpoints for pushing a table's rows out to a connected integration: list
      writable destinations, derive their write capabilities, and map export
      columns.
    name: table-writeback
  - description: >-
      Endpoints backing a lookup column's setup: the connections whose records a
      column could read, and the identity fields one record type can be looked
      up by.
    name: table-integration-lookup
  - description: >-
      Endpoints for sourcing leads from the lead database: count and preview
      matches, land them in a table, and keep saved searches. Alongside people
      and company searches, leads can be sourced from buying signals (what a
      company or person just did), with a catalog endpoint behind the picker
      that builds them.
    name: find-leads
  - description: >-
      Endpoints for discovering a domain's subdomains from public certificate
      logs and landing the results in a table.
    name: find-subdomains
  - description: Endpoints for the credit balance meter and usage reporting.
    name: credits
  - description: >-
      Endpoints for the workspace referral program: the shareable link, the
      friends who joined through it, and claiming a code after signup.
    name: referral
  - description: >-
      Endpoints for the affiliate program's own dashboard: enrolling and
      claiming a code, the summary, stats and activity feed, the commission
      ledger, and identity verification and payouts.
    name: affiliate
  - description: >-
      Endpoints for recording where a new workspace came from: the marketing
      page or campaign its signup link carried, sent once after signup.
    name: attribution
  - description: >-
      Endpoints for the design partner program's customer surface: whether this
      workspace is a design partner, the badges its feedback has earned, and
      sending and reading that feedback.
    name: design-partner
  - description: >-
      Endpoints for the org-level AI business context (company description,
      ideal customer profile, buyer personas, interest signals and social
      proof), plus domain-based generation and the reference documents whose
      summaries ride alongside those fields.
    name: ai-context
  - description: >-
      Endpoints for the signed-in user's Google Drive connection: starting and
      finishing the OAuth grant, checking or dropping it, and minting the
      short-lived token the Google Picker needs.
    name: google-drive
paths:
  /onboarding-wizard/own-runs/current/segment/:
    put:
      tags:
        - onboarding-wizard
      summary: Pick the audience of your own wizard run
      description: >-
        Picks one of the audiences the signed-in person's wizard run in their
        active workspace offers (the run `GET /own-runs/` lists), as the wizard
        page's pick does: finds 100 people of it, researches the top 10 and
        writes their first messages. Needs no session token: the sign-in finds
        the run, so an AI app connected to the workspace can pick it. 404 when
        the person has no run still to finish; 409 when the pick is refused
        where it stands (no such audience, too few people, people already
        found).
      operationId: choose_own_wizard_segment
      requestBody:
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/WizardSegmentChoiceSchema'
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/WizardRunReadSchema'
          description: Successful Response
        '401':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnauthorizedResponse'
          description: Unauthorized
        '403':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ForbiddenResponse'
          description: Forbidden
        '404':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/NotFoundResponse'
          description: >-
            There's no sequence being set up in this workspace. Start one from
            the company's website.
        '409':
          description: Not possible at this step of the preview.
        '422':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/UnprocessableEntityResponse'
          description: Invalid request made to the API.
        '429':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TooManyRequestsResponse'
          description: >-
            Too many requests (Retry-After says when to ask again), or the
            visitor's previews for the day are spent.
        '500':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServerErrorResponse'
          description: Internal server error.
        '502':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServerErrorResponse'
          description: Bad gateway error.
        '503':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServerErrorResponse'
          description: Service unavailable.
      security:
        - APIKeyHeader: []
        - HTTPBearer: []
components:
  schemas:
    WizardSegmentChoiceSchema:
      description: Pick one of the offered segments.
      properties:
        index:
          description: Which segment, from 0.
          minimum: 0
          title: Index
          type: integer
        switch:
          default: false
          description: >-
            Move a pick that stands to this segment: its people and messages are
            removed and this one's are found and written, at the preview's usual
            cost (`switch_credits`). Refused (409) while its first messages are
            still being written (`preview_settled`).
          title: Switch
          type: boolean
        timezone:
          anyOf:
            - maxLength: 64
              type: string
            - type: 'null'
          description: The visitor's browser clock, like Europe/Berlin.
          title: Timezone
      required:
        - index
      title: WizardSegmentChoiceSchema
      type: object
    WizardRunReadSchema:
      description: 'A preview: everything the wizard''s page shows.'
      properties:
        build_error:
          anyOf:
            - type: string
            - type: 'null'
          title: Build Error
        claimed:
          description: >-
            A visitor's preview was claimed: the workspace is a customer's now.
            Never true of a run in the person's own workspace, which nobody
            claims.
          title: Claimed
          type: boolean
        company_name:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The company's name as its homepage writes it; null until read, or
            when it names none.
          title: Company Name
        connect_credits:
          default: 0
          description: >-
            What Connect goes on to spend researching the people after the first
            twenty, said before the press.
          title: Connect Credits
          type: integer
        context:
          anyOf:
            - $ref: '#/components/schemas/WizardContextReadSchema'
            - type: 'null'
        credits_left:
          default: 0
          description: The workspace's credits left.
          title: Credits Left
          type: integer
        credits_per_person:
          default: 0
          description: What researching and writing to one person usually costs.
          title: Credits Per Person
          type: integer
        dns_issue:
          anyOf:
            - $ref: '#/components/schemas/WizardDnsIssue'
            - type: 'null'
        domain:
          title: Domain
          type: string
        headline:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The homepage's main headline, word for word; null until read, or
            when it has none.
          title: Headline
        id:
          format: uuid
          title: Id
          type: string
        insights_error:
          anyOf:
            - type: string
            - type: 'null'
          title: Insights Error
        join_requested_at:
          anyOf:
            - format: date-time
              type: string
            - type: 'null'
          title: Join Requested At
        launch_error:
          anyOf:
            - type: string
            - type: 'null'
          title: Launch Error
        launched_at:
          anyOf:
            - format: date-time
              type: string
            - type: 'null'
          title: Launched At
        learnings:
          description: >-
            What the writer already follows: the template's learnings and any
            saved since.
          items:
            type: string
          title: Learnings
          type: array
        logo_path:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The company's logo, a path under this API's address that needs no
            credentials (`/accounts/logos/{name}/`); null until one is found for
            its website.
          title: Logo Path
        messages:
          items:
            $ref: '#/components/schemas/WizardMessageReadSchema'
          title: Messages
          type: array
        outlook_available:
          description: >-
            Continue with Microsoft is offered: Outlook is open to every
            workspace (to this one, in your own workspace), as on Mailboxes.
            False shows the Outlook waitlist instead.
          title: Outlook Available
          type: boolean
        own_workspace:
          description: >-
            Started after sign-up in the person's own workspace: nothing is
            claimed at the end, and the Connect step only connects Gmail.
          title: Own Workspace
          type: boolean
        people:
          items:
            $ref: '#/components/schemas/WizardPersonReadSchema'
          title: People
          type: array
        people_covered:
          default: 0
          description: >-
            How many of the people the workspace's credits research and write
            to, which the wizard says in place of the hundred found.
          title: People Covered
          type: integer
        people_table_ready:
          description: >-
            The people table is made: its stream (`GET .../events/`) can be
            followed from now.
          title: People Table Ready
          type: boolean
        preview_settled:
          default: false
          description: >-
            Every first message of the picked audience is written or failed: a
            switch to another audience may start.
          title: Preview Settled
          type: boolean
        research:
          anyOf:
            - $ref: '#/components/schemas/WizardResearchReadSchema'
            - type: 'null'
        segment_index:
          anyOf:
            - type: integer
            - type: 'null'
          title: Segment Index
        segments:
          items:
            $ref: '#/components/schemas/WizardSegmentReadSchema'
          title: Segments
          type: array
        sender_name:
          anyOf:
            - type: string
            - type: 'null'
          title: Sender Name
        sender_source:
          anyOf:
            - $ref: '#/components/schemas/WizardSenderSource'
            - type: 'null'
        sender_title:
          anyOf:
            - type: string
            - type: 'null'
          title: Sender Title
        sequence_id:
          anyOf:
            - format: uuid
              type: string
            - type: 'null'
          title: Sequence Id
        stage:
          $ref: '#/components/schemas/WizardStage'
        stalled:
          description: >-
            The research's next step or the people's search never started:
            resume the preview to start it.
          title: Stalled
          type: boolean
        subheadline:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The sentence under that headline, word for word; null until read, or
            when none.
          title: Subheadline
        suggestions_full:
          default: false
          description: >-
            The run offers the most audiences it keeps while one can be picked:
            Suggest audiences is refused until one is picked.
          title: Suggestions Full
          type: boolean
        switch_credits:
          default: 0
          description: What switching to another audience usually costs before sign-up.
          title: Switch Credits
          type: integer
      required:
        - id
        - domain
        - own_workspace
        - stage
        - stalled
        - claimed
        - research
        - context
        - segments
        - segment_index
        - insights_error
        - build_error
        - sender_name
        - sender_title
        - sender_source
        - dns_issue
        - people_table_ready
        - people
        - messages
        - learnings
        - sequence_id
        - launched_at
        - launch_error
        - join_requested_at
        - outlook_available
      title: WizardRunReadSchema
      type: object
    UnauthorizedResponse:
      properties:
        detail:
          description: The detail of why the request is unauthorized.
          title: Detail
          type: string
      required:
        - detail
      title: UnauthorizedResponse
      type: object
    ForbiddenResponse:
      properties:
        detail:
          description: The detail of why the request is forbidden.
          title: Detail
          type: string
      required:
        - detail
      title: ForbiddenResponse
      type: object
    NotFoundResponse:
      properties:
        detail:
          description: The detail of why the resource was not found.
          title: Detail
          type: string
      required:
        - detail
      title: NotFoundResponse
      type: object
    UnprocessableEntityResponse:
      properties:
        detail:
          description: >-
            The detail of the error. This is the error message to show to the
            user. You should also use the issues field to show more detailed
            error messages per field. Use this field for a single liner error
            message.
          title: Detail
          type: string
        issues:
          description: >-
            The issues that caused the error. There can be multiple issues. Each
            issue is a user-facing error message.
          items:
            $ref: '#/components/schemas/UnprocessableEntityIssue'
          title: Issues
          type: array
      required:
        - detail
        - issues
      title: UnprocessableEntityResponse
      type: object
    TooManyRequestsResponse:
      properties:
        detail:
          description: The detail of why the request was refused for now.
          title: Detail
          type: string
      required:
        - detail
      title: TooManyRequestsResponse
      type: object
    ServerErrorResponse:
      properties:
        detail:
          description: The detail of why the server returned an error.
          title: Detail
          type: string
      required:
        - detail
      title: ServerErrorResponse
      type: object
    WizardContextReadSchema:
      description: What the research wrote about the company.
      properties:
        company_description:
          anyOf:
            - type: string
            - type: 'null'
          title: Company Description
        ideal_buyer_personas:
          anyOf:
            - type: string
            - type: 'null'
          title: Ideal Buyer Personas
        ideal_customer_profile:
          anyOf:
            - type: string
            - type: 'null'
          title: Ideal Customer Profile
        interest_signals:
          anyOf:
            - type: string
            - type: 'null'
          title: Interest Signals
        pilot_offer:
          anyOf:
            - type: string
            - type: 'null'
          title: Pilot Offer
        social_proof:
          anyOf:
            - type: string
            - type: 'null'
          title: Social Proof
      required:
        - company_description
        - ideal_customer_profile
        - ideal_buyer_personas
        - interest_signals
        - social_proof
        - pilot_offer
      title: WizardContextReadSchema
      type: object
    WizardDnsIssue:
      description: What the silent check of a company's sending setup found missing.
      enum:
        - no_dmarc
        - no_spf
      title: WizardDnsIssue
      type: string
    WizardMessageReadSchema:
      description: One person's first email and first LinkedIn message.
      properties:
        email_body:
          anyOf:
            - type: string
            - type: 'null'
          title: Email Body
        email_subject:
          anyOf:
            - type: string
            - type: 'null'
          title: Email Subject
        label:
          title: Label
          type: string
        linkedin_body:
          anyOf:
            - type: string
            - type: 'null'
          title: Linkedin Body
        looks_good:
          title: Looks Good
          type: boolean
        record_id:
          format: uuid
          title: Record Id
          type: string
        status:
          $ref: '#/components/schemas/WizardMessageStatus'
      required:
        - record_id
        - label
        - status
        - email_subject
        - email_body
        - linkedin_body
        - looks_good
      title: WizardMessageReadSchema
      type: object
    WizardPersonReadSchema:
      description: One person of the table.
      properties:
        company:
          title: Company
          type: string
        email:
          title: Email
          type: string
        email_status:
          anyOf:
            - $ref: '#/components/schemas/EmailDeliverability'
            - type: 'null'
          description: >-
            What the email check said of the address; null while it has said
            nothing.
        in_preview:
          description: Researched and written before sign-up (the top rows).
          title: In Preview
          type: boolean
        linkedin_url:
          title: Linkedin Url
          type: string
        name:
          title: Name
          type: string
        record_id:
          format: uuid
          title: Record Id
          type: string
        researched:
          title: Researched
          type: boolean
        title:
          title: Title
          type: string
        why:
          title: Why
          type: string
      required:
        - record_id
        - name
        - title
        - company
        - linkedin_url
        - in_preview
        - researched
        - email
        - email_status
        - why
      title: WizardPersonReadSchema
      type: object
    WizardResearchReadSchema:
      description: The business-context research, as it runs.
      properties:
        error:
          anyOf:
            - type: string
            - type: 'null'
          title: Error
        status:
          $ref: '#/components/schemas/AiContextGenerationStatus'
        steps:
          items:
            $ref: '#/components/schemas/AiStep'
          maxItems: 60
          title: Steps
          type: array
      required:
        - status
        - error
      title: WizardResearchReadSchema
      type: object
    WizardSegmentReadSchema:
      description: One audience on offer.
      properties:
        batch:
          description: >-
            Which batch offered it: 0 for the first, one more for each Edit's;
            each batch is listed best first.
          title: Batch
          type: integer
        companies:
          description: >-
            The companies they work at, in a line; empty when the search names
            none.
          title: Companies
          type: string
        counted:
          description: Whether the count was asked yet; false while it is still coming.
          title: Counted
          type: boolean
        description:
          title: Description
          type: string
        index:
          description: Where it stands among the segments offered, from 0.
          title: Index
          type: integer
        job_titles:
          description: >-
            The buyers by job title; empty on a segment kept before these were
            stored.
          items:
            type: string
          title: Job Titles
          type: array
        label:
          title: Label
          type: string
        matches:
          anyOf:
            - type: integer
            - type: 'null'
          description: >-
            How many people the search matched; null when not counted or not
            had.
          title: Matches
        reason:
          description: >-
            Why these people, for this business, in a sentence or two; empty
            when none.
          title: Reason
          type: string
        too_small:
          description: >-
            Counted under the 50 people an audience must match: not offered, and
            a pick of it is refused.
          title: Too Small
          type: boolean
        wanted:
          description: >-
            Who the visitor typed they want to reach, when the audience was
            written for it; empty for one suggested from the business context.
          title: Wanted
          type: string
      required:
        - index
        - label
        - description
        - job_titles
        - companies
        - matches
        - counted
        - reason
        - batch
        - too_small
        - wanted
      title: WizardSegmentReadSchema
      type: object
    WizardSenderSource:
      description: Where the name the messages are signed with came from.
      enum:
        - about_page
        - typed
        - sign_in
      title: WizardSenderSource
      type: string
    WizardStage:
      description: >-
        Where a run stands, derived from what it holds. Never stored.


        The frontend's five steps map onto these: researching and segments are
        step 1 and 2,

        finding is step 3, and writing is step 4 from the first message written
        (the page reads

        the messages themselves to tell).
      enum:
        - researching
        - research_failed
        - segments
        - finding
        - finding_failed
        - writing
        - launched
      title: WizardStage
      type: string
    UnprocessableEntityIssue:
      properties:
        input:
          anyOf:
            - type: string
            - type: integer
            - type: number
            - type: boolean
            - items: {}
              type: array
            - additionalProperties: true
              type: object
          description: The user's input that caused the error.
          title: Input
        loc:
          description: >-
            The location of the error. Always contains 1 or 2 elements. The
            first element is the type of location (e.g. 'body', 'query', 'path',
            'header'). The second element is the name of the field that caused
            the error. If the error is not related to a specific field, the
            second element is not present.
          items:
            type: string
          title: Loc
          type: array
        msg:
          description: The message of the error. The error message to show to the user.
          title: Msg
          type: string
        type:
          description: >-
            The type of the error. Useful for frontend code to handle different
            types of errors.
          title: Type
          type: string
      required:
        - loc
        - msg
        - type
        - input
      title: UnprocessableEntityIssue
      type: object
    WizardMessageStatus:
      description: Where the Preview stands on one person's first messages.
      enum:
        - writing
        - written
        - failed
      title: WizardMessageStatus
      type: string
    EmailDeliverability:
      description: >-
        The verdicts a Verify email column answers with, in the words its cells
        hold.


        The ``verify_email`` chain respells every supplier's verdict onto
        exactly

        these words (``email_verdict_canonical`` in ``table_enrichments``), so a

        sequence that reads the column compares its cells against them. Ordered

        from the safest to send to, which is the order the Audience tab lists
        them.
      enum:
        - valid
        - catch-all
        - risky
        - unknown
        - invalid
        - disposable
      title: EmailDeliverability
      type: string
    AiContextGenerationStatus:
      description: >-
        Where a context-generation job has got to.


        Jobs are stored ``PENDING``: committed, with the workflow that will work
        on

        them not yet started, which a crash between the two can leave for ever.
        The

        research's first step claims the job (``RUNNING``), and the deadline
        sweep

        fails one nothing ever claimed. A reader never sees ``PENDING``: to
        everyone

        outside the repository a job waiting for its workflow is already
        running.

        The two terminal states are absorbing: a job never leaves them.
      enum:
        - pending
        - running
        - succeeded
        - failed
      title: AiContextGenerationStatus
      type: string
    AiStep:
      additionalProperties: false
      description: >-
        One thing an AI turn did, as the wire spells it.


        Field-for-field identical to
        ``table_live_updates.TableCellActivityStepSchema``

        ON PURPOSE, and the duplication is the design. That schema sits in the
        table

        stratum's kernel, which the lead search, inbox and sequence surfaces
        have no

        business importing; this one sits under every surface equally. Because
        the

        two agree exactly, the frontend's ``TimelineStep`` renders both with no

        conversion and no second component, which is the property worth
        protecting.

        ``test_ai_step_mirrors_the_cell_activity_step`` pins them together.


        Plain strings rather than enums, for the same reason the cell schema
        uses

        them: the vocabulary is open, clients must tolerate tokens they have not

        learned yet, and a new action should never be able to break a running

        dashboard.
      properties:
        action:
          description: >-
            What kind of move this was, e.g. `read_table`, `plan`,
            `write_column`.
          title: Action
          type: string
        detail:
          default: ''
          description: >-
            The step's input: the instruction, the column it read, the query it
            ran.
          title: Detail
          type: string
        duration_ms:
          anyOf:
            - type: integer
            - type: 'null'
          description: Wall clock for the work this step describes, never an estimate.
          title: Duration Ms
        observation:
          default: ''
          description: >-
            One line on what came back. The half that makes a step worth
            reading.
          maxLength: 500
          title: Observation
          type: string
        outcome:
          default: completed
          description: >-
            `completed`, `failed`, `refused` or `stopped`. Clients must tolerate
            new tokens.
          title: Outcome
          type: string
        thought:
          anyOf:
            - type: string
            - type: 'null'
          description: >-
            The model's stated reasoning for choosing this step. Set by the
            agent loop; the assistant surfaces leave it null, and the renderer
            simply omits the rung.
          title: Thought
      required:
        - action
      title: AiStep
      type: object
  securitySchemes:
    APIKeyHeader:
      in: header
      name: X-API-Key
      type: apiKey
    HTTPBearer:
      scheme: bearer
      type: http

````

This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.